Step 2 - Create Synthesistable from Zotero export

Global settings

Clear work space and set global variables

# Clear memory
rm(list=ls()) # Clear environmental variables
gc() # memory garbage removal

          used  (Mb) gc trigger  (Mb) limit (Mb) max used  (Mb)
Ncells 4207633 224.8    7824414 417.9         NA  6840728 365.4
Vcells 7827112  59.8   14786712 112.9      16384 12513660  95.5

# set global options
knitr::opts_chunk$set(fig.width=12, fig.height=8, warning=FALSE, message=FALSE)

Load libaries

if(!require("pacman", quietly=T)) install.packages("pacman")
pacman::p_load(osfr,tinytex,tidyverse,keyring,knitr,readxl,data.table,colorspace, lpSolve,irr,here,lme4,broom,psych,zoo,units,ggdist,cowplot,ggcorrplot,dplyr, patchwork, cowplot, ggpmisc, forcats, pwr, ggpmisc, simstudy, explore, car,VIM,mice,flextable,here, remotes,magrittr,reshape2,descr,table1,tableone,gmodels,xtable,lavaan,corrplot,caret,corrgram,Hmisc,polycor,lavaan,kableExtra,DiagrammeR,grid,Gmisc,epitools)

Set up local tempfolder for raw and processed data files

# Get the path to the session's temporary directory
session_temp_dir <- tempdir()

# Define paths for the specific temporary subdirectories
raw_data_dir <- file.path(session_temp_dir, "raw_data")
processed_data_dir <- file.path(session_temp_dir, "processed_data")

# Create the 'raw_data' subdirectory if it doesn't exist
if (!dir.exists(raw_data_dir)) {
  dir.create(raw_data_dir)
}

# Create the 'processed_data' subdirectory if it doesn't exist
if (!dir.exists(processed_data_dir)) {
  dir.create(processed_data_dir)
}

 

Authenticate R to OSF connection

osf_auth(keyring :: key_get("osf"))

Registered PAT from the provided token

OSF nodes

# Define OSF node IDs at the beginning
# raw_data_node_id <- "yxsqb"   # Master Thesis Raw Data Node or other Raw Data Node
# raw_data_node_id <- "gpj2v"  # https://osf.io/gpj2v/ Quantify Occupational Injury
 raw_data_node_id <- "dpgby"  # https://osf.io/dpgby/ Art Business Education
# raw_data_node_id <- "z6jfn" # https://osf.io/z6jfn/ Housing prices
# raw_data_node_id <- "gu7ny" # https://osf.io/gu7ny/ Hmm53a-2425-GR1
# raw_data_node_id <- "prw4a" # https://osf.io/prw4a/ Hmm53a-2425-GR2
# raw_data_node_id <- "gxw3v" # https://osf.io/gxw3v/ Hmm53a-2425-GR3

# processed_data_node_id <- "e4rdh"  # Master Thesis Processed Data Node 
# processed_data_node_id <- "q4wgm"  # https://osf.io/q4wgm/ Quantify Occupational Injury
 processed_data_node_id <- "akgf2"  # https://osf.io/akgf2/ Art Business Education
# processed_data_node_id <- "6heqg"  # https://osf.io/6heqg/ Housing prices
# processed_data_node_id <- "76tn5"  # https://osf.io/76tn5/ Hmm53a-2425-GR1
# processed_data_node_id <- "ab6hg"  # https://osf.io/ab6hg/ Hmm53a-2425-GR2
# processed_data_node_id <- "tyhbk"  # https://osf.io/tyhbk/ Hmm53a-2425-GR3 

Download Zotero_tag_export_long.csv

osf_retrieve_node(processed_data_node_id) %>%
  osf_ls_files(pattern = "Zotero_tag_export_long.csv") %>%
   osf_download(path = raw_data_dir, conflicts="overwrite",progress=TRUE)

Load Zotero tag export file into R data frame

csv_file <- list.files(path = raw_data_dir, pattern = "\\.csv$", full.names = TRUE)

if (length(csv_file) == 0) {
  stop("Error: No csv file found in the specified directory.")
}



# standard pathname
csv_file[1] <- file.path(dirname(csv_file[1]), basename(csv_file[1]))
if (!file.exists(csv_file[1])) {
  stop("File does not exist. Check the path.")
}

print(csv_file)

[1] "/var/folders/v0/q9_by2r90yqg0g8s8rykvby40000gn/T//RtmplVKZdG/raw_data/Zotero_tag_export_long.csv"

Select first CSV file

# Read the Markdown file
Zotero_tag_export_long <- read.csv(csv_file[1], encoding = "UTF-8")

# Check if the file is empty
if (length(Zotero_tag_export_long) == 0) {
  stop("Error: The csv file is empty.")
}

own coding

Zotero_tag_export_long <- Zotero_tag_export_long %>%
  # Remove backslashes from the 'tag' column
  mutate(tag = gsub("\\\\", "", tag)) %>%
  # Update the annotation column by combining existing annotation, comment (if applicable), and page info
  mutate(annotation = str_squish(
    paste(
      if_else(is.na(annotation), "", annotation),
      if_else(comment != "No Comment", comment, ""),
      paste0("(p.", page, ")")
    )
  )) %>%
  # Remove the redundant page and comment columns
  select(-page, -comment)

# View the updated dataframe
print(Zotero_tag_export_long)

NA
NA

Zotero_SynthesisTable <- Zotero_tag_export_long %>%
  pivot_wider(
    id_cols = c(title, author),
    names_from = tag,
    values_from = annotation,
    values_fn = function(x) {
      if(length(x) == 1) {
        x
      } else {
        paste0('"', paste(x, collapse = '" "'), '"')
      }
    }
  ) %>%
  select(title, author, everything())

# View the transformed dataframe
print(Zotero_SynthesisTable)

NA

storage and cleaning

Upload Zotero tag export long data file to OSF

Save Zotero tag export long data frame to local processed_data_dir folder

# Define the full path for the output CSV file
output_file <- file.path(processed_data_dir, "Zotero_SynthesisTable.csv")

write.csv(Zotero_SynthesisTable,output_file,row.names=FALSE)

Upload Zotero tag export long file from local processed_data_dir to folder to OSF

Housekeeping

Delete files in local temp folder

Delete local directories

# Delete the raw_data_dir directory and its contents
# unlink(file.path(tempdir(), "raw_data_dir"), recursive = TRUE)
unlink(raw_data_dir, recursive = TRUE)

# Delete the processed_data_dir directory and its contents
# unlink(file.path(tempdir(), "processed_data_dir"), recursive = TRUE)
unlink(processed_data_dir, recursive = TRUE)